文章摘要

陈俊鹏,虞为.基于实时新闻分析的馆藏资源推荐方法研究[J].中国图书馆学报,2015,41(6):86~96
基于实时新闻分析的馆藏资源推荐方法研究
Library Resource Recommendation Based on Analysis onNewswires
投稿时间:2015-06-03  修订日期:2015-08-02
DOI:10.13530/j.cnki.jlis.156007
中文关键词: 馆藏资源  资源推荐  实时新闻  快数据处理  矩阵分解
英文关键词: Library resources  Resource recommendation  Real-time news  Fast data processing  Matrix factorization
基金项目:本文系国家社会科学基金青年项目“基于关联数据的图书馆语义云服务研究”(编号:12CTQ009)和江苏省社会科学基金青年项目“基于语义云服务的数字阅读推广研究”(编号:14TQC003)的研究成果之一
作者单位E-mail
陈俊鹏 南京大学信息管理学院 江苏 南京 210046 yuw.nju@gmail.com 
虞为 南京大学信息管理学院 江苏 南京 210046 yuw.nju@gmail.com,yuw.nju@gmail.com 
摘要点击次数: 3149
全文下载次数: 1728
中文摘要:
      如何在信息时代增加馆藏资源的可见度,提高馆藏资源的利用率,是一个急需研究和解决的问题。实时新闻和图书馆馆藏资源间的连接可以提高图书馆馆藏资源的可见度,增加图书馆馆藏资源的利用率,为用户提供丰富、全面的阅读资料和专业知识,帮助用户形成全面、深入阅读和思考的良好习惯。基于快数据处理技术的实时新闻分析和馆藏资源推荐框架,通过分析网络实时新闻获取用户感兴趣的话题,应用快数据处理技术、潜在语义分析、非负矩阵分解、权重矩阵分解等方法对数据进行语义分析和处理,对图书馆馆藏资源进行相关话题的分类和推荐。对OCLC的百万数据集和雅虎新闻的分析和实验表明,这种资源推荐框架和方法有较好的应用效果。图2。表1。
英文摘要:
There is a lack of research for providing professional domain knowledge and extending reading list to users who are interested in the special topics mentioned in the real time newswires. Meanwhile,there is a large scale of domain knowledge and application examples in library collections which can help users have a good understanding for those special topics. Hence,in this paper,we provide a novel method to link the corresponding real time news and records in the library. The extending reading list from the library can be recommended with the technology of natural language processing and semantic analysis.
We recommend the related library records to the users who are interested in the target news. We adopt natural language processing technology and LSA,NMF,and WMF methods to carry out our experiments.
We use the catalogue records corpora:WorldCat million dataset released by the OCLC in 2012. The dataset contains metadata records of nearly 12 million materials most widely held in libraries. The metadata contains approximately 80 million linked data triples,which can help users find the linked resources easily on the webFor the corpus of news articles,we collect the news articles of Yahoo! news from RSS feeds,dated from the 5th of April to 7th of July,2014,totally 95 daysIn order to get an objective observation of the performance,we randomly selected 500 news articles (about 10% of the news articles set)for evaluation. The results are evaluated with TOP10 recall hit rate,from which we can see WMF has better performance than LSA and NMF.
This newswire library linking offers a number of unique advantages to both libraries and information seekers:the up to dateness,the extensive coverage and comprehensiveness,the rich description. Using newswires as a complementary information resource in library catalogues addresses users information need by offering a vast pool of everyday life subject headings to complement the traditional library vocabularies constructed mainly by experts knowledge. For future work,we will involve library users in the evaluation of the system and make necessary improvements. 2 figs. 1 tab. 18 refs.
查看全文   查看/发表评论  下载PDF阅读器